Pepijn b6fb536460 chore(training): bump plan/memory dropout to 0.50 to force vision-grounding ...

After the recipe fix (target=${subtask} at every frame) the model
can still reach low text_loss by reading the answer off the plan in
the prompt: at training the prompt contains the 6-step plan, and the
current subtask is one of those steps, so the model just learns
"active step N matches subtask N" and never needs to look at the
image. Symptom at inference: subtask string is set but never updates
because the model isn't really conditioning on the visual progress.

Drop plan and memory with p=0.50 each — half of training frames the
prompt is just "${task}" (constant for this dataset) + visual prefix,
which is the only place the answer can come from. Forces the LM head
to actually use vision.

``subtask_dropout`` stays at 0.20 because subtask isn't in the
high-level prompt anymore (recipe fix removed the "Current subtask:
X" message); the knob still affects other sub-recipes that reference
it as context.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-12 21:31:00 +02:00

..

smolvla2_hirobot.slurm

chore(training): bump plan/memory dropout to 0.50 to force vision-grounding

2026-05-12 21:31:00 +02:00

train_policy.py

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00

train_with_streaming.py

feat(dependencies): minimal default tag install (#3362)

2026-04-12 20:03:04 +02:00